Skip to content

← ArchiveTalk2025

AI in Maya: Autodesk CEO and Animation Product Manager Demo MotionMaker, FaceAnimator and More

Andrew Anagnost, Lance Thornton

Autodesk University 2025 live demo by CEO Andrew Anagnost and Product Manager Lance Thornton showing Maya's MotionMaker locomotion synthesis, FaceAnimator, and additional AI-driven character animation tools.

Abstract

In this Autodesk University 2025 live demo, CEO Andrew Anagnost and product manager Lance Thornton show MotionMaker fully integrated into Maya generating plausible human locomotion from just a couple of spatial keyframes via live neural-network inference, trained on a large set of human motion data so it reproduces weight shifts, arm swing, and walk-to-run transitions. They demonstrate art-directing the result by adding a keyframe to redirect the character around a corner and regenerating on the fly. The session also previews FaceAnimator, which learns a character's facial and lip motion from existing animated sequences of a show and then generates face animation directly from an input audio file, and teases Autodesk Assistant scene editing in Maya driven by MCP servers.

How to read this

Category
Production talk / product demo (AI animation tools in Maya)
Contributions
  • Demonstrates MotionMaker generating plausible human locomotion from a couple of spatial keyframes via live neural-network inference
  • Shows art-directing the result by adding keyframes to redirect the character and regenerating on the fly
  • Previews FaceAnimator learning facial/lip motion from a show's existing sequences to drive face animation from audio, and teases MCP-driven Autodesk Assistant scene editing
Context
An Autodesk University product demo extending the MotionMaker AI animation direction (the earlier Meet MotionMaker introduction) into an integrated Maya feature set spanning locomotion synthesis, audio-driven face animation, and assistant-based scene editing.Builds on: Meet MotionMaker: New AI Animation Tool In Maya
Correctness
Vendor demo, not peer-reviewed; outputs depend on the underlying training data (large human-motion sets for locomotion, a show's own sequences for FaceAnimator) and are shown in curated live demos, so generalization and edit fidelity beyond the demo should be treated cautiously.
Clarity
Highly accessible; a single viewing conveys the capabilities and intended workflow.
How to read it
Watch for the keyframe-to-motion interaction model and how art direction is layered onto generated output; treat as a capability preview rather than a method, with no second pass needed for theory.

Builds on

Built upon by

Nothing yet.

Related work

Keywords

This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →